Several years ago Google researchers began constructing an articial brain consisting of 16,000 processor cores. The simulation was exposed to 10 million randomly selected YouTube video thumbnails over the course of three days and after being presented with a list of 20,000 different items, the artificial brain began to recognize photos of cats using a "deep learning algorithm", despite is was never fed information on distinguishing features that might help identify one. Google fellow Jeff Dean explains the simulation basically invented the concept of a cat. Full details at Wired.
Picking up on the most commonly occurring images featured on YouTube, the system achieved 81.7 percent accuracy in detecting human faces, 76.7 percent accuracy when identifying human body parts and 74.8 percent accuracy when identifying cats.
“Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not,” the team says in its paper, Building high-level features using large scale unsupervised learning, which it will present at the International Conference on Machine Learning in Edinburgh, 26 June-1 July.
“The network is sensitive to high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained it to obtain 15.8 percent accuracy in recognizing 20,000 object categories, a leap of 70 percent relative improvement over the previous state-of-the-art [networks].”